Enhancing Environmental Adaptability and Decision Transparency for Connected and Autonomous Vehicles
Bibliographic record
Abstract
To ensure the wide deployment of connected and autonomous vehicles (CAVs), both environmental adaptability and decision transparency are essential.With collective learning, CAVs can exchange and aggregate learning results, thus accelerating the learning process towards enhanced environmental adaptability.Meanwhile, integrating symbolic artificial intelligence (AI) into decision-making enhances decision transparency, thus gaining public trust.For this reason, this thesis aims to enhance the environmental adaptability and decision transparency of CAVs through collective learning and symbolic AI integration.Initially, a collective learning framework for connectionist AI, supported by multiaccess edge computing (MEC), is proposed.This framework allows CAVs to collectively and continuously aggregate learning results, leading to faster environmental adaptation.To further integrate symbolic AI into CAVs' high-level decision-making, expert knowledge in the form of logical rules is incorporated into the learning structure through a Markov Logic Network (MLN).This integration enables data-efficient learning and transparent decision-making.Next, the challenges of large-scale collective learning in symbolic AI are tackled by suggesting a hierarchical representation for ii exchanged learning results.Building on this hierarchical representation, a collective symbolic rule learning framework is proposed that encourages the sharing of learning results at different abstraction levels and learning stages.Extensive simulation results indicate that the proposed solutions enable CAVs to achieve faster environmental adaptation and transparent decision-making.Lastly, with the emergence of Large Language Models (LLMs), their role in expediting or automating learning tasks for CAVs is examined.LLMs' knowledge in the form of symbolic rules is further integrated with statistical learning to enhance robust and transparent decision-making, and a case study is presented to verify the performance of this integrated approach.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".